Digitized forging and pressing process regulation and control method and system
Through the digital forging process control method, the machine learning model is used to automatically calculate the forging process parameters, which solves the problem of insufficient automation in the existing technology and improves the pass rate and accuracy of the product.
Patent Information
- Application Number
- CN202510019776.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-07
- Publication Date
- 2025-05-23
AI Technical Summary
The existing forging process is insufficient automation, and the parameters of some forging process need to be manually selected and set, resulting in insufficient accuracy and prone to errors, which affects the pass rate of forging products.
Using digital forging process control methods, each parameter in the forging process, including heat treatment, forging and cooling parameters is automatically calculated and regulated by constructing a mapping relationship table, obtaining characteristic data of metal blanks, and performing input and output processing of machine learning models.
The digital regulation of the forging process is realized, the degree of automation is improved, manual intervention is reduced, and the pass rate and accuracy of forging products is improved.
Smart Images
Figure CN120023280A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field related to intelligent manufacturing, and in particular to a digital forging process control method and system. Background Art
[0002] Forging is an important metal processing technology. It uses a series of production processes to shape metal materials into various shapes and sizes. The working principle of the forging machine is to use pressure to place the metal material in the mold and cause it to undergo plastic deformation through the action of pressure. This process also includes heat treatment of the metal material and subsequent cooling, cutting and other processing processes.
[0003] The development of forging technology has gone through several stages. The earliest forging process was completely driven by human or animal power, such as forging hammers and forging machines. With the progress of industrialization, hydraulic and pneumatic forging presses gradually replaced human-driven forging presses, greatly improving work efficiency. Modern forging presses use electronics, computers and automation technology.
[0004] However, the existing forging process has insufficient automation, and some forging process parameters still need to be manually selected and set, which results in insufficient accuracy and prone to errors, affecting the qualification rate of forged products. Summary of the invention
[0005] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a digital forging process control method and system, aiming to solve the problems that the existing forging process has insufficient automation, some forging process parameters still need to be manually selected and set, there are insufficient accuracy and prone to errors, which affect the qualification rate of forging products.
[0006] In view of the above problems, the present application provides a digital forging process control method and system.
[0007] The first aspect disclosed in the present application provides a digital forging process control method, the method comprising the following steps: Step 1: construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specification and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specification of the workpiece, the overall size of the workpiece and the metal blank; Step 2: Acquire characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; Step 3: normalize the heat treatment parameters of the metal billet to generate heat treatment characteristic parameters of the metal billet; input the metal billet characteristic parameters and the metal billet heat treatment characteristic parameters into the trained second machine learning model to generate metal billet forging parameters; forge the metal billet to be forged according to the metal billet forging parameters to form a workpiece to be cooled; Step 4: Normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into the trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
[0008] Preferably, the step 1 specifically includes: Step 1.1: Construct a three-dimensional tensor as a mapping relationship table. The three tensor dimensions of the mapping relationship table are used to represent the overall specifications of the workpiece, the overall size of the workpiece, and the metal blank, respectively. The overall specifications of the workpiece are the steel type and shape of the workpiece, and the overall size of the workpiece is the volume of the workpiece. Step 1.2: Perform a search operation on the mapping relationship table according to the overall specification and the overall size of the workpiece, and retrieve the metal blank corresponding to the overall specification and the overall size of the workpiece as the selected metal blank.
[0009] Preferably, the step 2 specifically includes: Step 2.1: Acquire characteristic data of the selected metal blank, and perform normalization processing on the characteristic data of the metal blank to generate characteristic parameters of the metal blank, wherein the characteristic data of the metal blank includes steel type, volume, mass and hardness, and the normalization processing adopts maximum and minimum value normalization processing to map the characteristic data of the metal blank into characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 2.2: Inputting the characteristic parameters of the metal blank into the first machine learning model that has been trained, the first machine learning model is composed of a first fully connected neural network model and a second fully connected neural network model, the first fully connected neural network model outputs a heating temperature, and the second fully connected neural network model outputs a heating time, and the heating temperature and the heating time constitute the heat treatment parameters of the metal blank; Step 2.3: Heat-treat the metal blank according to the heating temperature and heating time in the metal blank heat treatment parameters to form a metal blank to be forged.
[0010] Preferably, the step 3 specifically includes: Step 3.1: Obtaining the heat treatment parameters of the metal blank, normalizing the heat treatment parameters of the metal blank, and generating the heat treatment characteristic parameters of the metal blank, wherein the normalization process adopts the maximum and minimum value normalization process, and is used to map the heat treatment parameters of the metal blank into the heat treatment characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 3.2: inputting the characteristic parameters of the metal billet and the characteristic parameters of the heat treatment of the metal billet into the trained second machine learning model, the second machine learning model is composed of a third fully connected neural network model and a fourth fully connected neural network model, the third fully connected neural network model outputs the pressing speed of the forging press, the fourth fully connected neural network model outputs the holding time of the forging press, and the pressing speed of the forging press and the holding time of the forging press constitute the forging parameters of the metal billet; Step 3.3: Forging the metal blank to be forged according to the forging machine's pressing speed and forging machine's holding time among the metal blank forging parameters to form a workpiece to be cooled.
[0011] Preferably, the step 4 specifically includes the following steps: Step 4.1: obtaining metal billet forging parameters, normalizing the metal billet forging parameters, and generating metal billet forging characteristic parameters, wherein the normalization process adopts maximum and minimum value normalization process, and is used to map the metal billet forging parameters into metal billet forging characteristic parameters whose value range is greater than or equal to 0 and less than or equal to 1; Step 4.2: inputting the metal billet characteristic parameters, the metal billet heat treatment characteristic parameters and the metal billet forging characteristic parameters into the trained third machine learning model, the third machine learning model is composed of the fifth fully connected neural network model and the sixth fully connected neural network model, the fifth fully connected neural network model outputs the cooling speed, the sixth fully connected neural network model outputs the cooling time, and the cooling speed and the cooling time constitute the metal billet cooling parameters; Step 4.3: Cool the workpiece to be cooled according to the cooling rate and cooling time in the metal billet cooling parameters to form a completed forging workpiece.
[0012] The second aspect disclosed in the present application provides a digital forging process control system, which is used for the above-mentioned digital forging process control method, and the system includes: A blank module, the blank module is used to construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specifications of the workpiece and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specifications of the workpiece, the overall size of the workpiece and the metal blank; A heat treatment module, wherein the heat treatment module is used to obtain characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; and heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; A forging module, wherein the forging module is used to normalize the heat treatment parameters of the metal blank to generate the heat treatment characteristic parameters of the metal blank; input the metal blank characteristic parameters and the heat treatment characteristic parameters of the metal blank into the trained second machine learning model to generate the metal blank forging parameters; forge the metal blank to be forged according to the metal blank forging parameters to form a workpiece to be cooled; A cooling module, wherein the cooling module is used to normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into a trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
[0013] The third aspect disclosed in the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned digital forging process control method when executing the computer program.
[0014] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned digital forging process control method are implemented.
[0015] The fifth aspect disclosed in the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the steps of the above-mentioned digital forging process control method.
[0016] The beneficial effects of the present invention are: (1) It realizes the digital control of the forging process, solving the problem that the existing forging process is not sufficiently automated and the parameters of the forging process need to be manually selected and set.
[0017] (2) Multiple machine learning models are used to calculate various parameters in the forging process flow with high accuracy, thereby improving the qualification rate of forging products. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 It is an overall flow chart of a digital forging process control method.
[0020] Figure 2 This is the overall structure diagram of a digital forging process control system. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0022] like Figure 1 As shown, the embodiment of the present application provides a digital forging process control method, the method comprising the following steps: Step 1: construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specification and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specification of the workpiece, the overall size of the workpiece and the metal blank; Step 2: Acquire characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; Step 3: normalize the heat treatment parameters of the metal billet to generate heat treatment characteristic parameters of the metal billet; input the metal billet characteristic parameters and the metal billet heat treatment characteristic parameters into the trained second machine learning model to generate metal billet forging parameters; forge the metal billet to be forged according to the metal billet forging parameters to form a workpiece to be cooled; Step 4: Normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into the trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
[0023] Furthermore, the step 1 specifically includes: Step 1.1: Construct a three-dimensional tensor as a mapping relationship table. The three tensor dimensions of the mapping relationship table are used to represent the overall specifications of the workpiece, the overall size of the workpiece, and the metal blank, respectively. The overall specifications of the workpiece are the steel type and shape of the workpiece, and the overall size of the workpiece is the volume of the workpiece. Step 1.2: Perform a search operation on the mapping relationship table according to the overall specification and the overall size of the workpiece, and retrieve the metal blank corresponding to the overall specification and the overall size of the workpiece as the selected metal blank.
[0024] Specifically, a three-dimensional tensor is constructed in the form of a Map as a mapping relationship table. The key of the Map is the overall specification of the workpiece, and the value is still a Map. Here, the key of the Map is the overall size of the workpiece, and the value is the metal billet.
[0025] Furthermore, the step 2 specifically includes: Step 2.1: Acquire characteristic data of the selected metal blank, and perform normalization processing on the characteristic data of the metal blank to generate characteristic parameters of the metal blank, wherein the characteristic data of the metal blank includes steel type, volume, mass and hardness, and the normalization processing adopts maximum and minimum value normalization processing to map the characteristic data of the metal blank into characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 2.2: Inputting the characteristic parameters of the metal blank into the first machine learning model that has been trained, the first machine learning model is composed of a first fully connected neural network model and a second fully connected neural network model, the first fully connected neural network model outputs a heating temperature, and the second fully connected neural network model outputs a heating time, and the heating temperature and the heating time constitute the heat treatment parameters of the metal blank; Step 2.3: Heat-treat the metal blank according to the heating temperature and heating time in the metal blank heat treatment parameters to form a metal blank to be forged.
[0026] Specifically, the steel types are mapped to numerical values in numerical order, and the maximum and minimum values are normalized together with the characteristic data of other metal billets. The outputs of the first fully connected neural network model and the second fully connected neural network model are unique hot vectors representing categories, which respectively represent the categories of heating temperature and heating time, that is, the heating temperatures include 100℃, 200℃, 300℃, 400℃, 500℃, 600℃, 700℃, 800℃, 900℃ and 1000℃, and the heating times include 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes, 35 minutes, 40 minutes, 45 minutes, 50 minutes, 55 minutes and 60 minutes.
[0027] Furthermore, the step 3 specifically includes: Step 3.1: Obtaining the heat treatment parameters of the metal blank, normalizing the heat treatment parameters of the metal blank, and generating the heat treatment characteristic parameters of the metal blank, wherein the normalization process adopts the maximum and minimum value normalization process, and is used to map the heat treatment parameters of the metal blank into the heat treatment characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 3.2: inputting the characteristic parameters of the metal billet and the characteristic parameters of the heat treatment of the metal billet into the trained second machine learning model, the second machine learning model is composed of a third fully connected neural network model and a fourth fully connected neural network model, the third fully connected neural network model outputs the pressing speed of the forging press, the fourth fully connected neural network model outputs the holding time of the forging press, and the pressing speed of the forging press and the holding time of the forging press constitute the forging parameters of the metal billet; Step 3.3: Forging the metal blank to be forged according to the forging machine's pressing speed and forging machine's holding time among the metal blank forging parameters to form a workpiece to be cooled.
[0028] Specifically, the outputs of the third fully connected neural network model and the fourth fully connected neural network model are unique hot vectors representing categories, which respectively represent the categories of the forging press pressing speed and the forging press holding time. That is, the forging press pressing speed has eight categories of 5mm / s, 7mm / s, 9mm / s, 11mm / s, 13mm / s, 15mm / s, 17mm / s and 19mm / s, and the forging press holding time has six categories of 1s, 2s, 3s, 4s, 5s and 6s.
[0029] Furthermore, the step 4 specifically includes the following steps: Step 4.1: obtaining metal billet forging parameters, normalizing the metal billet forging parameters, and generating metal billet forging characteristic parameters, wherein the normalization process adopts maximum and minimum value normalization process, and is used to map the metal billet forging parameters into metal billet forging characteristic parameters whose value range is greater than or equal to 0 and less than or equal to 1; Step 4.2: inputting the metal billet characteristic parameters, the metal billet heat treatment characteristic parameters and the metal billet forging characteristic parameters into the trained third machine learning model, the third machine learning model is composed of the fifth fully connected neural network model and the sixth fully connected neural network model, the fifth fully connected neural network model outputs the cooling speed, the sixth fully connected neural network model outputs the cooling time, and the cooling speed and the cooling time constitute the metal billet cooling parameters; Step 4.3: Cool the workpiece to be cooled according to the cooling rate and cooling time in the metal billet cooling parameters to form a completed forging workpiece.
[0030] Specifically, the outputs of the fifth fully connected neural network model and the sixth fully connected neural network model are unique hot vectors representing categories, which respectively represent the categories of cooling speed and cooling time, that is, the cooling speed has three categories: fast, medium and slow, and the cooling time has six categories: 30s, 60s, 90s, 120s, 150s and 180s.
[0031] Specifically, the training data sets of the first machine learning model, the second machine learning model, and the third machine learning model are constructed by collecting and manually annotating a large amount of previous optimal forging process control data. The training data sets are divided into training sets and test sets in a ratio of 8 to 2.
[0032] Specifically, the learning rate of the first machine learning model, the second machine learning model, and the third machine learning model during training is set to 0.001. The training process uses the Adam optimizer, and Dropout is performed to prevent overfitting. The loss function uses the cross entropy loss function.
[0033] In summary, the digital forging process control method provided in the embodiment of the present application has the following technical effects: (1) It realizes the digital control of the forging process, solving the problem that the existing forging process is not sufficiently automated and the parameters of the forging process need to be manually selected and set.
[0034] (2) Multiple machine learning models are used to calculate various parameters in the forging process flow with high accuracy, thereby improving the qualification rate of forging products.
[0035] Based on the same inventive concept as the digital forging process control method in the above-mentioned embodiment, Figure 2 As shown, the present application provides a digital forging process control system, the system comprising: A blank module, the blank module is used to construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specifications of the workpiece and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specifications of the workpiece, the overall size of the workpiece and the metal blank; A heat treatment module, wherein the heat treatment module is used to obtain characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; and heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; A forging module, wherein the forging module is used to normalize the heat treatment parameters of the metal blank to generate the heat treatment characteristic parameters of the metal blank; input the metal blank characteristic parameters and the heat treatment characteristic parameters of the metal blank into the trained second machine learning model to generate the metal blank forging parameters; forge the metal blank to be forged according to the metal blank forging parameters to form a workpiece to be cooled; A cooling module, wherein the cooling module is used to normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into a trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
[0036] Through the above-mentioned detailed description of a digital forging process control method in this specification, those skilled in the art can clearly understand a digital forging process control system in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0037] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above-mentioned digital forging process control method when executing the computer program.
[0038] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned digital forging process control method are implemented.
[0039] In one embodiment, a computer program product is provided, including a computer program or instructions, which implement the steps of the above-mentioned digital forging process control method when executed by a processor.
[0040] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0041] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A digital forging process control method, characterized in that: The method comprises the following steps: Step 1: construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specification and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specification of the workpiece, the overall size of the workpiece and the metal blank; Step 2: Acquire characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; Step 3: normalize the heat treatment parameters of the metal billet to generate heat treatment characteristic parameters of the metal billet; input the metal billet characteristic parameters and the metal billet heat treatment characteristic parameters into the trained second machine learning model to generate metal billet forging parameters; forge the metal billet to be forged according to the metal billet forging parameters to form a workpiece to be cooled; Step 4: Normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into the trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
2. A digital forging process control method as claimed in claim 1, characterized in that: The step 1 specifically includes: Step 1.1: Construct a three-dimensional tensor as a mapping relationship table. The three tensor dimensions of the mapping relationship table are used to represent the overall specifications of the workpiece, the overall size of the workpiece, and the metal blank, respectively. The overall specifications of the workpiece are the steel type and shape of the workpiece, and the overall size of the workpiece is the volume of the workpiece. Step 1.2: Perform a search operation on the mapping relationship table according to the overall specification and the overall size of the workpiece, and retrieve the metal blank corresponding to the overall specification and the overall size of the workpiece as the selected metal blank.
3. A digital forging process control method as claimed in claim 1, characterized in that: The step 2 specifically includes: Step 2.1: Acquire characteristic data of the selected metal blank, and perform normalization processing on the characteristic data of the metal blank to generate characteristic parameters of the metal blank, wherein the characteristic data of the metal blank includes steel type, volume, mass and hardness, and the normalization processing adopts maximum and minimum value normalization processing to map the characteristic data of the metal blank into characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 2.2: Inputting the characteristic parameters of the metal blank into the first machine learning model that has been trained, the first machine learning model is composed of a first fully connected neural network model and a second fully connected neural network model, the first fully connected neural network model outputs a heating temperature, and the second fully connected neural network model outputs a heating time, and the heating temperature and the heating time constitute the heat treatment parameters of the metal blank; Step 2.3: Heat-treat the metal blank according to the heating temperature and heating time in the metal blank heat treatment parameters to form a metal blank to be forged.
4. A digital forging process control method as claimed in claim 1, characterized in that: The step 3 specifically includes: Step 3.1: Obtaining the heat treatment parameters of the metal blank, normalizing the heat treatment parameters of the metal blank, and generating the heat treatment characteristic parameters of the metal blank, wherein the normalization process adopts the maximum and minimum value normalization process, and is used to map the heat treatment parameters of the metal blank into the heat treatment characteristic parameters of the metal blank with a value range greater than or equal to 0 and less than or equal to 1; Step 3.2: inputting the characteristic parameters of the metal billet and the characteristic parameters of the heat treatment of the metal billet into the trained second machine learning model, the second machine learning model is composed of a third fully connected neural network model and a fourth fully connected neural network model, the third fully connected neural network model outputs the pressing speed of the forging press, the fourth fully connected neural network model outputs the holding time of the forging press, and the pressing speed of the forging press and the holding time of the forging press constitute the forging parameters of the metal billet; Step 3.3: Forging the metal blank to be forged according to the forging machine's pressing speed and forging machine's holding time among the metal blank forging parameters to form a workpiece to be cooled.
5. A digital forging process control method as claimed in claim 1, characterized in that: The step 4 specifically comprises the following steps: Step 4.1: obtaining metal billet forging parameters, normalizing the metal billet forging parameters, and generating metal billet forging characteristic parameters, wherein the normalization process adopts maximum and minimum value normalization process, and is used to map the metal billet forging parameters into metal billet forging characteristic parameters whose value range is greater than or equal to 0 and less than or equal to 1; Step 4.2: inputting the metal billet characteristic parameters, the metal billet heat treatment characteristic parameters and the metal billet forging characteristic parameters into the trained third machine learning model, the third machine learning model is composed of the fifth fully connected neural network model and the sixth fully connected neural network model, the fifth fully connected neural network model outputs the cooling speed, the sixth fully connected neural network model outputs the cooling time, and the cooling speed and the cooling time constitute the metal billet cooling parameters; Step 4.3: Cool the workpiece to be cooled according to the cooling rate and cooling time in the metal billet cooling parameters to form a completed forging workpiece.
6. A digital forging process control system, the system comprising: A blank module, the blank module is used to construct a mapping relationship table, and select a metal blank from the mapping relationship table according to the overall specifications of the workpiece and the overall size of the workpiece, wherein the mapping relationship table is used to store the corresponding relationship between the overall specifications of the workpiece, the overall size of the workpiece and the metal blank; A heat treatment module, wherein the heat treatment module is used to obtain characteristic data of the selected metal blank, and normalize the characteristic data of the metal blank to generate characteristic parameters of the metal blank; input the characteristic parameters of the metal blank into the trained first machine learning model to generate heat treatment parameters of the metal blank; and heat treat the metal blank according to the heat treatment parameters of the metal blank to form a metal blank to be forged; A forging module, wherein the forging module is used to normalize the heat treatment parameters of the metal blank to generate the heat treatment characteristic parameters of the metal blank; input the metal blank characteristic parameters and the heat treatment characteristic parameters of the metal blank into the trained second machine learning model to generate the metal blank forging parameters; forge the metal blank to be forged according to the metal blank forging parameters to form a workpiece to be cooled; A cooling module, wherein the cooling module is used to normalize the metal billet forging parameters to generate metal billet forging characteristic parameters; input the metal billet characteristic parameters, metal billet heat treatment characteristic parameters and metal billet forging characteristic parameters into a trained third machine learning model to generate metal billet cooling parameters; cool the workpiece to be cooled according to the metal billet cooling parameters to form a completed forged workpiece.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of a digital forging process control method described in any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a digital forging process control method described in any one of claims 1 to 5 are implemented.
9. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of a digital forging process control method described in any one of claims 1 to 5 are implemented.